arXiv Statistics ML
CausalWAM: Learning the Causes of Actions in World Action Models
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
Sep 22
OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling
arXiv:2609.23753v1 Announce Type: cross Abstract: Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeli...
arXiv AI
Jul 22
DWM: Separating World Effects from Actions in Latent World Models
arXiv:2607. 18715v1 Announce Type: new Abstract: Latent world models underpin much of modern model-based control, yet current action-conditioned formulations supervise the next-latent transition with a single, undifferentiated target, forcing a monolithic learning signal to absorb every source of state change.
arXiv Computer Vision
Sep 30
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
arXiv:2609.34981v2 Announce Type: replace Abstract: World action models (WAMs) predict the future alongside actions during training. Due to the heavy computation cost of video denoising, whether the...
arXiv AI
Sep 17
CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models
The paper introduces CSWAM, a Causal Semantic World Action Model that enhances FastWAM by integrating a causal semantic expert based on V-JEPA 2.1. This expert provides temporally grounded, appearance‑agnostic representations of semantic state changes and motion, leveraging sparse observation history and causal attention to improve action‑only inference. Experiments on simulation and real‑robot tasks show that CSWAM significantly boosts out‑of‑distribution generalization, raising success rates from 10.16% to 45.18% on RoboTwin 2.0 and from 27.5% to 70.0% across real‑robot tasks.
arXiv Computer Vision
Oct 8
Long-WAM: Scaling the Context of World-Action Models
arXiv:2610.10528v1 Announce Type: cross Abstract: Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Lon...
arXiv Computer Vision
Sep 30
EVO-WAM: Evolving World Action Models through Video-Action Verification
arXiv:2609.38057v1 Announce Type: new Abstract: Improving robot policies on new tasks without collecting additional expert demonstrations remains a central challenge in robot learning. World action m...